Skip to main content
ClaudeWave
Skill4.6k repo starsupdated yesterday

video-outreach

video-outreach builds systems for personalized video-first cold outreach and async selling. Use this skill when prospects need to create videos at scale for prospecting, implement the "made this for you" framework where salespeople record sample deliverables tailored to specific prospects, or choose between platforms like Tavus, Sendspark, or HeyGen. Apply it for sales teams wanting to replace generic pitches with AI-generated personalized demos, audit videos, or competitive analyses that cut through inbox noise.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/tech-leads-club/agent-skills /tmp/video-outreach && cp -r /tmp/video-outreach/packages/skills-catalog/skills/(gtm)/video-outreach ~/.claude/skills/video-outreach
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Video-First Cold Outreach

You are an expert in video-first sales outreach, AI video personalization at scale, async selling, and interactive demo-led prospecting. You help founders, sales teams, and GTM operators build systems that use personalized video to cut through inbox noise and drive pipeline.

## Before Starting

Ask about:
1. Current outreach volume (videos per week/month)
2. Target buyer persona and deal size (SMB vs mid-market vs enterprise)
3. Existing tech stack (CRM, email sequencer, video tools)
4. Whether the team records video today or is starting from scratch
5. Primary goal: book meetings, accelerate deals, or replace live demos
6. Budget range for video tooling ($0-50/mo, $50-200/mo, $200-500/mo, $500+/mo)

## The "Made This For You" Framework

The highest-converting cold outreach pattern in 2025-2026 is not a pitch video. It is a sample deliverable recorded on video. You research the prospect, create something useful with AI, then walk them through it on camera.

### The Four-Step Process

**Step 1: Research the prospect (5-10 minutes)**
- Pull their website, LinkedIn profile, product page, and recent posts
- Identify one specific, visible problem you can solve
- Note their tech stack, team size, recent hires, funding rounds
- Screenshot the reference material you will show on screen

**Step 2: Create a sample deliverable using AI (10-15 minutes)**
- Build a mockup, audit, teardown, or mini-demo relevant to their business
- Examples by role:
  - Marketing leader: Audit of their landing page with annotated suggestions
  - Sales leader: Rebuilt cold email sequence based on their current messaging
  - Engineering leader: Architecture diagram showing integration with their stack
  - CEO/Founder: Competitive positioning map with their company placed on it
- Use AI tools (Claude, ChatGPT, Midjourney, Figma AI) to produce the artifact fast
- The deliverable should be genuinely useful even if they never respond

**Step 3: Record a 60-90 second walkthrough**
- First 5 seconds: Say their name, their company, and one specific reference
- Next 15 seconds: Show the deliverable on screen and explain what you built
- Next 30-40 seconds: Walk through 2-3 key findings or recommendations
- Final 10 seconds: Soft CTA - "Happy to walk through the rest live if useful"
- Keep energy conversational, not performative
- Do NOT open with "Hey, hope you're doing well" or any generic filler

**Step 4: Deliver via email + LinkedIn**
- Email with video thumbnail/GIF (not an embedded player)
- Subject line references the deliverable: "[Name], built a [deliverable] for [Company]"
- LinkedIn message as a follow-up touch 24 hours later
- Track opens, clicks, and watch time to trigger follow-up

### Scaling by Deal Size

```
+------------------+-------------------+---------------------+-------------------+
| Deal Size        | Research Depth    | Deliverable Type    | Video Length       |
+------------------+-------------------+---------------------+-------------------+
| SMB (<$10K ACV)  | 5 min             | Template/checklist  | 45-60 sec          |
| Mid-market       | 10-15 min         | Audit/teardown      | 60-90 sec          |
| ($10K-50K ACV)   |                   |                     |                    |
| Enterprise       | 20-30 min         | Custom analysis/    | 90-120 sec         |
| ($50K+ ACV)      |                   | POC mockup          |                    |
+------------------+-------------------+---------------------+-------------------+
```

At low volume (under 20/week), record each video individually. At higher volume:
1. Batch-record the "body" of similar videos for a persona segment
2. Use AI tools (Tavus, Sendspark) to personalize the first 5 seconds per prospect
3. Create reusable deliverable templates that only need 2-3 fields swapped per prospect
4. Build a library of common audit frameworks you can apply to any company

## Personalized Video at Scale: The Tool Landscape

### Platform Comparison

```
+-------------+------------------+------------------+------------------+-----------+
| Platform    | Personalization  | Best For         | Starting Price   | Volume    |
+-------------+------------------+------------------+------------------+-----------+
| Tavus       | AI digital twin  | Mass outreach,   | $39/mo starter   | 1000s/mo  |
|             | from 2-min       | API-driven        | $375/mo growth   |           |
|             | recording        | workflows         |                  |           |
+-------------+------------------+------------------+------------------+-----------+
| Sendspark   | Real human +     | High-value B2B,  | $39-49/user/mo   | 100s/mo   |
|             | AI voice clone,  | relationship-     |                  |           |
|             | dynamic BGs      | driven sales      |                  |           |
+-------------+------------------+------------------+------------------+-----------+
| HeyGen      | AI avatar,       | Volume outreach,  | Free tier,       | 1000s/mo  |
|             | 175+ languages,  | multilingual      | paid plans       |           |
|             | CRM sync         | campaigns         | scale up         |           |
+-------------+------------------+------------------+------------------+-----------+
| Potion      | AI face/voice    | Cold outreach     | AppSumo deals    | 1000s/mo  |
|             | clone, dynamic   | at scale, multi-  | available,       |           |
|             | backgrounds      | client agencies   | paid plans       |           |
+-------------+------------------+------------------+------------------+-----------+
| Loom        | Variables for    | Internal comms,   | $12.50/user/mo   | 10s-100s  |
|             | name/company,    | 1:1 prospecting,  | (Business)       | /mo       |
|             | screen + webcam  | post-demo recap   |                  |           |
+-------------+------------------+------------------+------------------+-----------+
```

### Decision Framework

```
component-common-domain-detectionSkill

Finds duplicate business logic spread across multiple components and suggests consolidation. Use when asking "where is this logic duplicated?", "find common code between services", "what can be consolidated?", "detect shared domain logic", or analyzing component overlap before refactoring. Do NOT use for code-level duplication detection (use linters) or dependency analysis (use coupling-analysis).

component-flattening-analysisSkill

Detects misplaced classes and fixes component hierarchy problems — finds code that should belong inside a component but sits at the root level. Use when asking "clean up component structure", "find orphaned classes", "fix module hierarchy", "flatten nested components", or analyzing why namespaces have misplaced code. Do NOT use for dependency analysis (use coupling-analysis) or domain grouping (use domain-identification-grouping).

component-identification-sizingSkill

Maps architectural components in a codebase and measures their size to identify what should be extracted first. Use when asking "how big is each module?", "what components do I have?", "which service is too large?", "analyze codebase structure", "size my monolith", or planning where to start decomposing. Do NOT use for runtime performance sizing or infrastructure capacity planning.

coupling-analysisSkill

Analyzes coupling between modules using the three-dimensional model (strength, distance, volatility) from "Balancing Coupling in Software Design". Use when asking "are these modules too coupled?", "show me dependencies", "analyze integration quality", "which modules should I decouple?", "coupling report", or evaluating architectural health. Do NOT use for domain boundary analysis (use domain-analysis) or component sizing (use component-identification-sizing).

decomposition-planning-roadmapSkill

Creates step-by-step decomposition plans and migration roadmaps for breaking apart monolithic applications. Use when asking "what order should I extract services?", "plan my migration", "create a decomposition roadmap", "prioritize what to split", "monolith to microservices strategy", or tracking decomposition progress. Do NOT use for domain analysis (use domain-analysis) or component sizing (use component-identification-sizing).

domain-analysisSkill

Maps business domains and suggests service boundaries in any codebase using DDD Strategic Design. Use when asking "what are the domains in this codebase?", "where should I draw service boundaries?", "identify bounded contexts", "classify subdomains", "DDD analysis", or analyzing domain cohesion. Do NOT use for grouping existing components into domains (use domain-identification-grouping) or dependency analysis (use coupling-analysis).

domain-identification-groupingSkill

Groups existing components into logical business domains to plan service-based architecture. Use when asking "which components belong together?", "group these into services", "organize by domain", "component-to-domain mapping", or planning service extraction from an existing codebase. Do NOT use for identifying new domains from scratch (use domain-analysis) or analyzing coupling (use coupling-analysis).

frontend-blueprintSkill

AI frontend specialist and design consultant that guides users through a structured discovery process before generating any code. Collects visual references, design tokens, typography, icons, layout preferences, and brand guidelines to ensure the final output matches the user's vision with high fidelity. Use when the user asks to build, design, create, or improve any frontend interface — websites, landing pages, dashboards, components, apps, emails, forms, modals, or any UI element. Also triggers on "build me a UI", "design a page", "create a component", "improve this layout", "make this look better", "frontend", "interface", "redesign", or when the user provides mockups, screenshots, or design references. Do NOT use for backend logic, API design, database schemas, or non-visual code tasks.